Unsupervised Neural Text Generation by Stochastic Searching

自然语言生成(NLG)是人工智能的一个重要领域。NLG的目标是在各种任务中合成自然语言文本(例如句子)，包括文本摘要、释义生成和对话系统。最先进的NLG系统基于深度神经网络，它通常通过自回归方式一次预测一个单词来合成一个句子。这些方法在表现力和自然度方面明显优于传统的基于规则/模板的NLG。然而，现有的神经NLG有两个主要缺陷：1)神经网络通常是数据饥饿型的。例如，训练神经翻译系统需要数百万对平行句子。2)由于自回归的性质(例如，从左到右的生成)，这些方法遭受了“错误累积”问题，即，随着生成的进行，文本的质量可能会急剧下降。这项研究的长期目标是调查文本生成的非监督方法。在我们以前的研究中，我们通过从变分自动编码器的概率连续潜在空间进行采样来解决这个问题。最近，我们提出了一种新型的Metropolis-Hastings(MH)采样器，它直接从离散的词空间中采样句子。这样，文本生成将更加数据高效，并且可以很容易地适应各种现实世界的应用。在我们以前工作的基础上，本研究项目将系统地探索随机搜索的无监督文本生成，短期目标如下：1)随机搜索算法的发展。尽管我们有MH采样器，但我计划探索随机搜索算法，如模拟退火法和遗传算法，因为大多数NLG任务更好地被描述为离散优化问题，而不是抽样。在这里，我们还将设计适合于文本生成的搜索操作(例如，词/短语编辑)。它们以分布式的方式在整个句子中执行编辑，因此我们的方法不会受到“错误累积”问题的影响。2)无监督文本生成的应用。我们的搜索框架提供了一种灵活的文本生成方法，因为我们可以很容易地操作搜索目标函数，而且这种方法不需要并行数据来进行训练。我计划解决NLP中的几个重要的生成任务，包括文本摘要、句子简化和风格转换文本生成。3)搜索与学习相结合的文本生成方法。我想把我们的搜索算法整合到一个可学习的模型中。一方面，参数学习模型不仅可以平滑人工定义的搜索目标，而且可以提高句子生成的推理效率。另一方面，搜索过程也可以帮助训练学习机器，特别是在强化学习环境中。

Natural language generation (NLG) is an important field of artificial intelligence. NLG aims to synthesize natural language text (e.g., sentences) in a variety of tasks, including text summarization, paraphrase generation, and dialogue systems. State-of-the-art NLG systems are based on deep neural networks, which typically synthesize a sentence by predicting one word at a time in an autoregressive fashion. Such approaches significantly outperform traditional rule/template-based NLG in terms of expressiveness and naturalness. However, existing neural NLG has two major drawbacks: 1) Neural networks are usually data-hungry. For example, millions of pairs of parallel sentences are required to train a neural translation system. 2) These methods suffer from the "error accumulation" problem, i.e., the quality of text could drop drastically as the generation proceeds, due to the autoregressive nature (e.g., left-to-right generation). The long-term goal of this proposed research is to investigate unsupervised approaches to text generation. In our previous studies, we tackled this problem by sampling from the probabilistic continuous latent space of a variational autoencoder. More recently, we proposed a novel Metropolis-Hastings (MH) sampler that directly samples a sentence from the discrete word space. In this way, text generation would be more data-efficient, and could be easily adapted to various real-world applications. Based on our previous work, this proposed research program would systematically explore unsupervised text generation by stochastic search, with the following short-term goals: 1) Development of stochastic searching algorithms. Despite our MH sampler, I plan to explore stochastic search algorithms, such as simulated annealing and genetic algorithms, because most NLG tasks are better formulated as a discrete optimization problem than sampling. Here, we would also design searching operations (e.g., word/phrase editing) suitable for text generation. They perform edits in a distributed way over the entire sentence, so our approach does not suffer from the "error accumulation" problem. 2) Applications of unsupervised text generation. Our searching framework provides a flexible way of text generation, because we can easily manipulate the searching objective function and also because such approach does not require parallel data for training. I plan to address a few important generation tasks in NLP, including text summarization, sentence simplification, and style-transfer text generation. 3) Combining searching and learning for text generation. I would like to integrate our search algorithms into a learnable model. On the one hand, a parametric learning model could not only smooth the manually defined searching objective, but also improve inference efficiency for sentence generation. On the other hand, the search procedure could also help train a learning machine, especially in the reinforcement learning setting.